Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import pandas as pd
-import torch
+import torch                              # ← This was missing
 from transformers import pipeline
 import nltk
 from nltk.corpus import stopwords
@@ -8,8 +8,6 @@ from nltk.stem import WordNetLemmatizer
 import re
 import string
 
-st.set_page_config(page_title="Daily Mirror News Classifier", page_icon="📰")
-
 # ====================== PREPROCESSING ======================
 nltk.download('stopwords', quiet=True)
 nltk.download('wordnet', quiet=True)
@@ -30,31 +28,18 @@ def preprocess_text(text):
     return ' '.join(tokens)
 
 # ====================== LOAD MODEL ======================
-@st.cache_resource(show_spinner=False)
+@st.cache_resource
 def load_model():
-    model_name = "Ginidu2003/Distilbert-Base-News-classifier"
-    hf_token = st.secrets.get("HF_TOKEN")   # Reads the secret you added
-
-    try:
-        pipe = pipeline(
-            "text-classification",
-            model=model_name,
-            token=hf_token,                    # ← This fixes most 403 errors
-            device=0 if torch.cuda.is_available() else -1
-        )
-        st.success("✅ Model loaded successfully!")
-        return pipe
-    except Exception as e:
-        st.error("❌ Failed to load model")
-        st.error(str(e))
-        return None
+    model_name = "Ginidu2003/Distilbert-Base-News-classifier"   # ← Change if your model name is different
+    return pipeline(
+        "text-classification",
+        model=model_name,
+        device=0 if torch.cuda.is_available() else -1
+    )
 
 classifier = load_model()
 
-if classifier is None:
-    st.stop()
-
-# ====================== APP ======================
+# ====================== STREAMLIT APP ======================
 st.title("📰 Daily Mirror News Classifier")
 st.subheader("Classify news into Business, Opinion, Political Gossip, Sports, or World News")
 
@@ -64,6 +49,7 @@ uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
 
 if uploaded_file is not None:
     df = pd.read_csv(uploaded_file)
+    
     st.write("### Preview of uploaded data")
     st.dataframe(df.head())
 
@@ -75,7 +61,7 @@ if uploaded_file is not None:
             
             predictions = []
             for text in df['clean_content']:
-                if not text.strip():
+                if text.strip() == "":
                     predictions.append("Unknown")
                 else:
                     result = classifier(text)[0]
@@ -85,8 +71,10 @@ if uploaded_file is not None:
             df = df.drop(columns=['clean_content'], errors='ignore')
             
             st.success("✅ Classification completed!")
+            st.write("### Preview of classified data")
             st.dataframe(df.head())
 
+            # Download button
             csv = df.to_csv(index=False).encode('utf-8')
             st.download_button(
                 label="📥 Download output.csv",